PDF Support + MORE!!!! (#416)
# Added - Added support for PDFs within Kavita. PDFs will open in the Manga reader and you can read through them as images. PDFs are heavier than archives, so they may take longer to open for reading. (Fixes #187) # Changed - Changed: Major change in how Kavita libraries work. Kavita libraries will now allow for mixed media types, that means you can have raw images, archives, epubs, and pdfs all within your Manga library. In the case that the same Series exists between 2 different types of medias, they will be separated and an icon will show to help you identify the types. The correct reader will open regardless of what library you are on. Note: Nightly users need to delete their Raw Images libraries before updating. # Fixed - Fixed: Fixed an issue where checking if a file was modified since last scan always returned true, meaning we would do more I/O than was needed (Fixes #415) - Fixed: There wasn't enough spacing on the top menu bar on the Manga reader - Fixed: Fixed a bug where user preferences dark mode control always showed true, even if you were not using dark mode # Dev stuff - For image extraction, if there is only 1 image we will extract just that, else we will extract only images - Refactored all the Parser code out of the ScannerService into a self contained class. The class should be created for any scans, allowing multiple tasks to run without any chance of cross over. * Fixed indentation for cs files * Fixed an issue where the logic for if a file had been modified or not was not working and always saying modified, meaning we were doing more file I/O than needed. * Implemented the ability to have PDF books. No reader functionality. * Implemented a basic form of scanning for PDF files. Reworked Image based libraries to remove the need to separate in a special library and instead just work within the Manga/Comic library. * Removed the old library types. * Removed some extra code around old raw library types * Fully implemented PDF support into Kavita by using docnet. Removed old libraries we tried that did not work. PDFs take about 200ms to save the file to disk, so they are much slower than reading archives. * Refactored Libraries so that they can have any file extension and the UI will decide which reader to use. * Reworked the Series Parsing code. We now use a separate instance for each task call, so there should be no cross over if 2 tasks are running at the same time. Second, we now store Format with the Series, so we can have duplicate Series with the same name, but a different type of files underneath. * Fixed PDF transparency issues - Used this code to fix an issue when a PDF page doesn't have a background. https://github.com/GowenGit/docnet/issues/8#issuecomment-538985672 - This also fixes the same issue for cover images * Fixed an issue where if a raw image was in a directory with non-image files, those would get moved to cache when trying to open the file. * For image extraction, if there is only 1 image, just copy that to cache instead of everything else in the directory that is an image. * Add some spacing to the top menu bar * Added an icon to the card to showcase the type of file * Added a tag badge to the series detail page * Fixed a bug in user preferences where dark mode control would default to true, even if you weren't on it * Fixed some tests up * Some code smells Co-authored-by: Robbie Davis <robbie@therobbiedavis.com>
This commit is contained in:
Joseph Milazzo
GitHub
parent
b8165b311c
commit
b0df67cdda
43 changed files with 1725 additions and 577 deletions
198
API/Services/Tasks/Scanner/ParseScannedFiles.cs
Normal file
198
API/Services/Tasks/Scanner/ParseScannedFiles.cs
Normal file
|
|
@ -0,0 +1,198 @@
|
|||
using System;
|
||||
using System.Collections.Concurrent;
|
||||
using System.Collections.Generic;
|
||||
using System.Diagnostics;
|
||||
using System.IO;
|
||||
using System.Linq;
|
||||
using API.Entities.Enums;
|
||||
using API.Interfaces.Services;
|
||||
using API.Parser;
|
||||
using Microsoft.Extensions.Logging;
|
||||
|
||||
namespace API.Services.Tasks.Scanner
|
||||
{
|
||||
public class ParsedSeries
|
||||
{
|
||||
public string Name { get; init; }
|
||||
public string NormalizedName { get; init; }
|
||||
public MangaFormat Format { get; init; }
|
||||
}
|
||||
|
||||
|
||||
public class ParseScannedFiles
|
||||
{
|
||||
private readonly ConcurrentDictionary<ParsedSeries, List<ParserInfo>> _scannedSeries;
|
||||
private readonly IBookService _bookService;
|
||||
private readonly ILogger _logger;
|
||||
|
||||
/// <summary>
|
||||
/// An instance of a pipeline for processing files and returning a Map of Series -> ParserInfos.
|
||||
/// Each instance is separate from other threads, allowing for no cross over.
|
||||
/// </summary>
|
||||
/// <param name="bookService"></param>
|
||||
/// <param name="logger"></param>
|
||||
public ParseScannedFiles(IBookService bookService, ILogger logger)
|
||||
{
|
||||
_bookService = bookService;
|
||||
_logger = logger;
|
||||
_scannedSeries = new ConcurrentDictionary<ParsedSeries, List<ParserInfo>>();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Processes files found during a library scan.
|
||||
/// Populates a collection of <see cref="ParserInfo"/> for DB updates later.
|
||||
/// </summary>
|
||||
/// <param name="path">Path of a file</param>
|
||||
/// <param name="rootPath"></param>
|
||||
/// <param name="type">Library type to determine parsing to perform</param>
|
||||
private void ProcessFile(string path, string rootPath, LibraryType type)
|
||||
{
|
||||
ParserInfo info;
|
||||
|
||||
if (Parser.Parser.IsEpub(path))
|
||||
{
|
||||
info = _bookService.ParseInfo(path);
|
||||
}
|
||||
else
|
||||
{
|
||||
info = Parser.Parser.Parse(path, rootPath, type);
|
||||
}
|
||||
|
||||
if (info == null)
|
||||
{
|
||||
_logger.LogWarning("[Scanner] Could not parse series from {Path}", path);
|
||||
return;
|
||||
}
|
||||
|
||||
if (Parser.Parser.IsEpub(path) && Parser.Parser.ParseVolume(info.Series) != Parser.Parser.DefaultVolume)
|
||||
{
|
||||
info = Parser.Parser.Parse(path, rootPath, type);
|
||||
var info2 = _bookService.ParseInfo(path);
|
||||
info.Merge(info2);
|
||||
}
|
||||
|
||||
TrackSeries(info);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Attempts to either add a new instance of a show mapping to the _scannedSeries bag or adds to an existing.
|
||||
/// This will check if the name matches an existing series name (multiple fields) <see cref="MergeName"/>
|
||||
/// </summary>
|
||||
/// <param name="info"></param>
|
||||
private void TrackSeries(ParserInfo info)
|
||||
{
|
||||
if (info.Series == string.Empty) return;
|
||||
|
||||
// Check if normalized info.Series already exists and if so, update info to use that name instead
|
||||
info.Series = MergeName(info);
|
||||
|
||||
var existingKey = _scannedSeries.Keys.FirstOrDefault(ps =>
|
||||
ps.Format == info.Format && ps.NormalizedName == Parser.Parser.Normalize(info.Series));
|
||||
existingKey ??= new ParsedSeries()
|
||||
{
|
||||
Format = info.Format,
|
||||
Name = info.Series,
|
||||
NormalizedName = Parser.Parser.Normalize(info.Series)
|
||||
};
|
||||
|
||||
|
||||
|
||||
_scannedSeries.AddOrUpdate(existingKey, new List<ParserInfo>() {info}, (_, oldValue) =>
|
||||
{
|
||||
oldValue ??= new List<ParserInfo>();
|
||||
if (!oldValue.Contains(info))
|
||||
{
|
||||
oldValue.Add(info);
|
||||
}
|
||||
|
||||
return oldValue;
|
||||
});
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Using a normalized name from the passed ParserInfo, this checks against all found series so far and if an existing one exists with
|
||||
/// same normalized name, it merges into the existing one. This is important as some manga may have a slight difference with punctuation or capitalization.
|
||||
/// </summary>
|
||||
/// <param name="info"></param>
|
||||
/// <returns></returns>
|
||||
public string MergeName(ParserInfo info)
|
||||
{
|
||||
var normalizedSeries = Parser.Parser.Normalize(info.Series);
|
||||
_logger.LogDebug("Checking if we can merge {NormalizedSeries}", normalizedSeries);
|
||||
var existingName =
|
||||
_scannedSeries.SingleOrDefault(p => Parser.Parser.Normalize(p.Key.NormalizedName) == normalizedSeries && p.Key.Format == info.Format)
|
||||
.Key;
|
||||
if (existingName != null && !string.IsNullOrEmpty(existingName.Name))
|
||||
{
|
||||
_logger.LogDebug("Found duplicate parsed infos, merged {Original} into {Merged}", info.Series, existingName.Name);
|
||||
return existingName.Name;
|
||||
}
|
||||
|
||||
return info.Series;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
///
|
||||
/// </summary>
|
||||
/// <param name="libraryType">Type of library. Used for selecting the correct file extensions to search for and parsing files</param>
|
||||
/// <param name="folders">The folders to scan. By default, this should be library.Folders, however it can be overwritten to restrict folders</param>
|
||||
/// <param name="totalFiles">Total files scanned</param>
|
||||
/// <param name="scanElapsedTime">Time it took to scan and parse files</param>
|
||||
/// <returns></returns>
|
||||
public Dictionary<ParsedSeries, List<ParserInfo>> ScanLibrariesForSeries(LibraryType libraryType, IEnumerable<string> folders, out int totalFiles,
|
||||
out long scanElapsedTime)
|
||||
{
|
||||
var sw = Stopwatch.StartNew();
|
||||
totalFiles = 0;
|
||||
var searchPattern = GetLibrarySearchPattern(libraryType);
|
||||
foreach (var folderPath in folders)
|
||||
{
|
||||
try
|
||||
{
|
||||
totalFiles += DirectoryService.TraverseTreeParallelForEach(folderPath, (f) =>
|
||||
{
|
||||
try
|
||||
{
|
||||
ProcessFile(f, folderPath, libraryType);
|
||||
}
|
||||
catch (FileNotFoundException exception)
|
||||
{
|
||||
_logger.LogError(exception, "The file {Filename} could not be found", f);
|
||||
}
|
||||
}, searchPattern, _logger);
|
||||
}
|
||||
catch (ArgumentException ex)
|
||||
{
|
||||
_logger.LogError(ex, "The directory '{FolderPath}' does not exist", folderPath);
|
||||
}
|
||||
}
|
||||
|
||||
scanElapsedTime = sw.ElapsedMilliseconds;
|
||||
_logger.LogInformation("Scanned {TotalFiles} files in {ElapsedScanTime} milliseconds", totalFiles,
|
||||
scanElapsedTime);
|
||||
|
||||
return SeriesWithInfos();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Given the Library Type, returns the regex pattern that restricts which files types will be found during a file scan.
|
||||
/// </summary>
|
||||
/// <param name="libraryType"></param>
|
||||
/// <returns></returns>
|
||||
private static string GetLibrarySearchPattern(LibraryType libraryType)
|
||||
{
|
||||
return Parser.Parser.SupportedExtensions;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Returns any series where there were parsed infos
|
||||
/// </summary>
|
||||
/// <returns></returns>
|
||||
private Dictionary<ParsedSeries, List<ParserInfo>> SeriesWithInfos()
|
||||
{
|
||||
var filtered = _scannedSeries.Where(kvp => kvp.Value.Count > 0);
|
||||
var series = filtered.ToDictionary(v => v.Key, v => v.Value);
|
||||
return series;
|
||||
}
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue